Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2179 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.1010. Min Act: -0.0001

Data Index: 563928 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.9768. Min Act: -0.0001

Data Index: 3823 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0467. Min Act: -0.0001

Data Index: 708778 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.9509. Min Act: -0.0001

Data Index: 472779 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8832. Min Act: -0.0001

Data Index: 463618 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8722. Min Act: -0.0001

Data Index: 709106 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8624. Min Act: -0.0001

Data Index: 56978 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8427. Min Act: -0.0001

Data Index: 1341164 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8141. Min Act: -0.0001

Data Index: 691026 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8661. Min Act: -0.0001

Data Index: 943284 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.7963. Min Act: -0.0001

Data Index: 1057094 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8270. Min Act: -0.0001

Data Index: 38660 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8349. Min Act: -0.0001

Data Index: 663587 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8310. Min Act: -0.0001

Data Index: 814997 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.7742. Min Act: -0.0001

Data Index: 996100 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.7599. Min Act: -0.0001

Data Index: 79231 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.7590. Min Act: -0.0001

Data Index: 1058101 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.7850. Min Act: -0.0001

Data Index: 154541 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.7365. Min Act: -0.0001

Data Index: 427606 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.7480. Min Act: -0.0001

Data Index: 560051 (C4 (Web Text))

Max Activating Token Index: 739